lov-clone-rebrand
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted template files (source code, READMEs, and i18n configurations) and user-supplied rebranding metadata to perform its core functions. This creates a surface where malicious instructions embedded in templates could potentially influence the agent's behavior during the modification process.
- Ingestion points: Local template files and rebranding metadata provided in the request context.
- Boundary markers: Absent; the instructions do not define delimiters to separate instructions from the data being processed.
- Capability inventory: File system read/write, Git operations (commit, push), and execution of deployment CLI tools.
- Sanitization: Not implemented for the content being replaced.
- [COMMAND_EXECUTION]: The skill utilizes local Python scripts (
profile_store.py,validate_skill.py) and development tools like Git and npx to perform configuration and project modification tasks. These operations are scoped to the skill's utility and involve persistent storage in the user's config directory.
Audit Metadata